1/* 2 * Altivec optimized MP3 decoding functions 3 * Copyright (c) 2010 Vitor Sessak 4 * 5 * This file is part of FFmpeg. 6 * 7 * FFmpeg is free software; you can redistribute it and/or 8 * modify it under the terms of the GNU Lesser General Public 9 * License as published by the Free Software Foundation; either 10 * version 2.1 of the License, or (at your option) any later version. 11 * 12 * FFmpeg is distributed in the hope that it will be useful, 13 * but WITHOUT ANY WARRANTY; without even the implied warranty of 14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 15 * Lesser General Public License for more details. 16 * 17 * You should have received a copy of the GNU Lesser General Public 18 * License along with FFmpeg; if not, write to the Free Software 19 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 20 */ 21 22#include "config.h" 23#include "libavutil/attributes.h" 24#include "libavutil/cpu.h" 25#include "libavutil/internal.h" 26#include "libavutil/mem_internal.h" 27#include "libavutil/ppc/cpu.h" 28#include "libavutil/ppc/util_altivec.h" 29#include "libavcodec/mpegaudiodsp.h" 30 31#if HAVE_ALTIVEC 32 33#define MACS(rt, ra, rb) rt+=(ra)*(rb) 34#define MLSS(rt, ra, rb) rt-=(ra)*(rb) 35 36#define SUM8(op, sum, w, p) \ 37{ \ 38 op(sum, (w)[0 * 64], (p)[0 * 64]); \ 39 op(sum, (w)[1 * 64], (p)[1 * 64]); \ 40 op(sum, (w)[2 * 64], (p)[2 * 64]); \ 41 op(sum, (w)[3 * 64], (p)[3 * 64]); \ 42 op(sum, (w)[4 * 64], (p)[4 * 64]); \ 43 op(sum, (w)[5 * 64], (p)[5 * 64]); \ 44 op(sum, (w)[6 * 64], (p)[6 * 64]); \ 45 op(sum, (w)[7 * 64], (p)[7 * 64]); \ 46} 47 48static void apply_window(const float *buf, const float *win1, 49 const float *win2, float *sum1, float *sum2, int len) 50{ 51 const vector float *win1a = (const vector float *) win1; 52 const vector float *win2a = (const vector float *) win2; 53 const vector float *bufa = (const vector float *) buf; 54 vector float *sum1a = (vector float *) sum1; 55 vector float *sum2a = (vector float *) sum2; 56 vector float av_uninit(v0), av_uninit(v4); 57 vector float v1, v2, v3; 58 59 len = len >> 2; 60 61#define MULT(a, b) \ 62 { \ 63 v1 = vec_ld(a, win1a); \ 64 v2 = vec_ld(b, win2a); \ 65 v3 = vec_ld(a, bufa); \ 66 v0 = vec_madd(v3, v1, v0); \ 67 v4 = vec_madd(v2, v3, v4); \ 68 } 69 70 while (len--) { 71 v0 = vec_xor(v0, v0); 72 v4 = vec_xor(v4, v4); 73 74 MULT( 0, 0); 75 MULT( 256, 64); 76 MULT( 512, 128); 77 MULT( 768, 192); 78 MULT(1024, 256); 79 MULT(1280, 320); 80 MULT(1536, 384); 81 MULT(1792, 448); 82 83 vec_st(v0, 0, sum1a); 84 vec_st(v4, 0, sum2a); 85 sum1a++; 86 sum2a++; 87 win1a++; 88 win2a++; 89 bufa++; 90 } 91} 92 93static void apply_window_mp3(float *in, float *win, int *unused, float *out, 94 ptrdiff_t incr) 95{ 96 LOCAL_ALIGNED_16(float, suma, [17]); 97 LOCAL_ALIGNED_16(float, sumb, [17]); 98 LOCAL_ALIGNED_16(float, sumc, [17]); 99 LOCAL_ALIGNED_16(float, sumd, [17]); 100 101 float sum; 102 int j; 103 float *out2 = out + 32 * incr; 104 105 /* copy to avoid wrap */ 106 memcpy(in + 512, in, 32 * sizeof(*in)); 107 108 apply_window(in + 16, win , win + 512, suma, sumc, 16); 109 apply_window(in + 32, win + 48, win + 640, sumb, sumd, 16); 110 111 SUM8(MLSS, suma[0], win + 32, in + 48); 112 113 sumc[ 0] = 0; 114 sumb[16] = 0; 115 sumd[16] = 0; 116 117 out[0 ] = suma[ 0]; 118 out += incr; 119 out2 -= incr; 120 for(j=1;j<16;j++) { 121 *out = suma[ j] - sumd[16-j]; 122 *out2 = -sumb[16-j] - sumc[ j]; 123 out += incr; 124 out2 -= incr; 125 } 126 127 sum = 0; 128 SUM8(MLSS, sum, win + 16 + 32, in + 32); 129 *out = sum; 130} 131 132#endif /* HAVE_ALTIVEC */ 133 134av_cold void ff_mpadsp_init_ppc(MPADSPContext *s) 135{ 136#if HAVE_ALTIVEC 137 if (!PPC_ALTIVEC(av_get_cpu_flags())) 138 return; 139 140 s->apply_window_float = apply_window_mp3; 141#endif /* HAVE_ALTIVEC */ 142} 143